© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23841
    Prev
    Next
    INDEX
    Explanations

    Technical texts and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autom
    -0.27
    .AutoSize
    -0.27
     AUT
    -0.26
     autism
    -0.25
    è½®
    -0.25
     alternating
    -0.24
    èĩªåĬ¨
    -0.24
     Adler
    -0.24
    autor
    -0.24
    åĭ¢
    -0.24
    POSITIVE LOGITS
    _b
    0.48
     bon
    0.44
    -b
    0.43
    bon
    0.42
    B
    0.41
     Brow
    0.41
    ðĿijı
    0.41
     B
    0.40
    *b
    0.40
     Brett
    0.40
    Activations Density 0.020%

    No Known Activations